chaiml-ssnew-v7-1a-dpo-cosine

developer_uid: chai_backend_admin

submission_id: chaiml-ssnew-v7-1a-dpo-cosine_v1

model_name: training123

model_group: ChaiML/ssnew-v7-1a-dpo_c

status: torndown

timestamp: 2025-11-23T23:21:21+00:00

num_battles: 5720

num_wins: 2903

celo_rating: 1300.28

family_friendly_score: 0.542

family_friendly_standard_error: 0.007046076922657033

submission_type: basic

model_repo: ChaiML/ssnew-v7-1a-dpo_cosine

model_architecture: MistralForCausalLM

model_num_parameters: 24096691200.0

best_of: 8

max_input_tokens: 2048

max_output_tokens: 64

reward_model: default

latencies: [{'batch_size': 1, 'throughput': 0.36447621478831976, 'latency_mean': 2.7435606610774994, 'latency_p50': 2.309441924095154, 'latency_p90': 4.385750126838684}, {'batch_size': 3, 'throughput': 0.832258068132599, 'latency_mean': 3.5993696069717407, 'latency_p50': 3.602235794067383, 'latency_p90': 3.9779831409454345}, {'batch_size': 5, 'throughput': 0.9943288449265872, 'latency_mean': 4.997237809896469, 'latency_p50': 4.985968708992004, 'latency_p90': 5.607950973510742}, {'batch_size': 6, 'throughput': 1.0589057967963078, 'latency_mean': 5.641819684505463, 'latency_p50': 5.639685273170471, 'latency_p90': 6.348651885986328}, {'batch_size': 10, 'throughput': 1.1560269444341293, 'latency_mean': 8.573677209615708, 'latency_p50': 8.562956690788269, 'latency_p90': 9.759244203567505}]

gpu_counts: {'NVIDIA A100-SXM4-80GB': 1}

display_name: training123

is_internal_developer: True

language_model: ChaiML/ssnew-v7-1a-dpo_cosine

model_size: 24B

ranking_group: single

throughput_3p7s: 0.85

us_pacific_date: 2025-11-20

win_ratio: 0.5075174825174825

generation_params: {'temperature': 1.0, 'top_p': 1.0, 'min_p': 0.0, 'top_k': 80, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['</s>', 'User:', 'You:', '\n'], 'max_input_tokens': 2048, 'best_of': 8, 'max_output_tokens': 64}

formatter: {'memory_template': "{bot_name}'s Persona: {memory}\n####\n", 'prompt_template': '', 'bot_template': '{bot_name}: {message}\n', 'user_template': '{user_name}: {message}\n', 'response_template': '####\n{bot_name}:', 'truncate_by_message': True}

Resubmit model

Shutdown handler not registered because Python interpreter is not running in the main thread
run pipeline %s
run pipeline stage %s
Running pipeline stage MKMLizer
Starting job with name chaiml-ssnew-v7-1a-dpo-cosine-v1-mkmlizer
Waiting for job on chaiml-ssnew-v7-1a-dpo-cosine-v1-mkmlizer to finish
chaiml-ssnew-v7-1a-dpo-cosine-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-ssnew-v7-1a-dpo-cosine-v1-mkmlizer: ║                                                                     ║
chaiml-ssnew-v7-1a-dpo-cosine-v1-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-ssnew-v7-1a-dpo-cosine-v1-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-ssnew-v7-1a-dpo-cosine-v1-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-ssnew-v7-1a-dpo-cosine-v1-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-ssnew-v7-1a-dpo-cosine-v1-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-ssnew-v7-1a-dpo-cosine-v1-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-ssnew-v7-1a-dpo-cosine-v1-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-ssnew-v7-1a-dpo-cosine-v1-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-ssnew-v7-1a-dpo-cosine-v1-mkmlizer: ║                                                                     ║
chaiml-ssnew-v7-1a-dpo-cosine-v1-mkmlizer: ║  Version: 0.30.2                                                    ║
chaiml-ssnew-v7-1a-dpo-cosine-v1-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-ssnew-v7-1a-dpo-cosine-v1-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-ssnew-v7-1a-dpo-cosine-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-ssnew-v7-1a-dpo-cosine-v1-mkmlizer: ║                                                                     ║
chaiml-ssnew-v7-1a-dpo-cosine-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-ssnew-v7-1a-dpo-cosine-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-ssnew-v7-1a-dpo-cosine-v1-mkmlizer: ║                                                                     ║
chaiml-ssnew-v7-1a-dpo-cosine-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-ssnew-v7-1a-dpo-cosine-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-ssnew-v7-1a-dpo-cosine-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-ssnew-v7-1a-dpo-cosine-v1-mkmlizer: ║                                                                     ║
chaiml-ssnew-v7-1a-dpo-cosine-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-ssnew-v7-1a-dpo-cosine-v1-mkmlizer: Downloaded to shared memory in 104.109s
chaiml-ssnew-v7-1a-dpo-cosine-v1-mkmlizer: Checking if ChaiML/ssnew-v7-1a-dpo_cosine already exists in ChaiML
chaiml-ssnew-v7-1a-dpo-cosine-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpz3dm78kw, device:0
chaiml-ssnew-v7-1a-dpo-cosine-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-ssnew-v7-1a-dpo-cosine-v1-mkmlizer: quantized model in 47.235s
chaiml-ssnew-v7-1a-dpo-cosine-v1-mkmlizer: Processed model ChaiML/ssnew-v7-1a-dpo_cosine in 151.345s
chaiml-ssnew-v7-1a-dpo-cosine-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-ssnew-v7-1a-dpo-cosine-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-ssnew-v7-1a-dpo-cosine-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-ssnew-v7-1a-dpo-cosine-v1/nvidia
chaiml-ssnew-v7-1a-dpo-cosine-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-ssnew-v7-1a-dpo-cosine-v1/nvidia/config.json
chaiml-ssnew-v7-1a-dpo-cosine-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-ssnew-v7-1a-dpo-cosine-v1/nvidia/special_tokens_map.json
chaiml-ssnew-v7-1a-dpo-cosine-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-ssnew-v7-1a-dpo-cosine-v1/nvidia/tokenizer_config.json
chaiml-ssnew-v7-1a-dpo-cosine-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-ssnew-v7-1a-dpo-cosine-v1/nvidia/tokenizer.json
chaiml-ssnew-v7-1a-dpo-cosine-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-ssnew-v7-1a-dpo-cosine-v1/nvidia/flywheel_model.0.safetensors
chaiml-ssnew-v7-1a-dpo-cosine-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-ssnew-v7-1a-dpo-cosine-v1/nvidia/flywheel_model.1.safetensors
chaiml-ssnew-v7-1a-dpo-cosine-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 4/363 [00:00<00:09, 39.41it/s]
Loading 0:   2%|▏         | 8/363 [00:00<00:11, 31.28it/s]
Loading 0:   3%|▎         | 12/363 [00:00<00:10, 33.83it/s]
Loading 0:   4%|▍         | 16/363 [00:00<00:11, 30.01it/s]
Loading 0:   6%|▌         | 21/363 [00:00<00:09, 34.77it/s]
Loading 0:   7%|▋         | 25/363 [00:00<00:11, 30.39it/s]
Loading 0:   9%|▉         | 32/363 [00:00<00:08, 36.90it/s]
Loading 0:  10%|▉         | 36/363 [00:01<00:15, 21.45it/s]
Loading 0:  11%|█         | 40/363 [00:01<00:15, 21.53it/s]
Loading 0:  12%|█▏        | 43/363 [00:01<00:16, 19.33it/s]
Loading 0:  13%|█▎        | 48/363 [00:01<00:14, 21.17it/s]
Loading 0:  14%|█▍        | 51/363 [00:02<00:16, 19.13it/s]
Loading 0:  16%|█▌        | 57/363 [00:02<00:23, 12.95it/s]
Loading 0:  16%|█▋        | 59/363 [00:02<00:23, 12.85it/s]
Loading 0:  18%|█▊        | 65/363 [00:03<00:16, 18.10it/s]
Loading 0:  19%|█▉        | 70/363 [00:03<00:15, 18.82it/s]
Loading 0:  20%|██        | 73/363 [00:03<00:16, 17.55it/s]
Loading 0:  22%|██▏       | 79/363 [00:03<00:12, 22.96it/s]
Loading 0:  23%|██▎       | 82/363 [00:03<00:12, 23.20it/s]
Loading 0:  24%|██▎       | 86/363 [00:04<00:12, 22.30it/s]
Loading 0:  25%|██▍       | 89/363 [00:04<00:11, 23.25it/s]
Loading 0:  25%|██▌       | 92/363 [00:04<00:13, 19.80it/s]
Loading 0:  27%|██▋       | 99/363 [00:04<00:09, 27.10it/s]
Loading 0:  28%|██▊       | 102/363 [00:04<00:10, 24.90it/s]
Loading 0:  29%|██▉       | 107/363 [00:04<00:11, 23.00it/s]
Loading 0:  31%|███       | 112/363 [00:05<00:09, 25.74it/s]
Loading 0:  32%|███▏      | 115/363 [00:05<00:09, 25.50it/s]
Loading 0:  33%|███▎      | 120/363 [00:05<00:08, 28.49it/s]
Loading 0:  34%|███▍      | 123/363 [00:05<00:09, 25.71it/s]
Loading 0:  36%|███▌      | 129/363 [00:05<00:07, 30.73it/s]
Loading 0:  37%|███▋      | 133/363 [00:05<00:07, 28.96it/s]
Loading 0:  38%|███▊      | 138/363 [00:05<00:07, 31.36it/s]
Loading 0:  39%|███▉      | 142/363 [00:06<00:07, 29.37it/s]
Loading 0:  41%|████      | 148/363 [00:06<00:05, 36.09it/s]
Loading 0:  42%|████▏     | 152/363 [00:06<00:08, 24.66it/s]
Loading 0:  43%|████▎     | 156/363 [00:06<00:08, 24.15it/s]
Loading 0:  44%|████▍     | 159/363 [00:06<00:08, 23.06it/s]
Loading 0:  45%|████▌     | 165/363 [00:06<00:07, 27.90it/s]
Loading 0:  47%|████▋     | 169/363 [00:07<00:07, 26.38it/s]
Loading 0:  48%|████▊     | 174/363 [00:07<00:06, 29.33it/s]
Loading 0:  49%|████▉     | 178/363 [00:07<00:06, 27.42it/s]
Loading 0:  50%|█████     | 182/363 [00:07<00:06, 28.12it/s]
Loading 0:  52%|█████▏    | 187/363 [00:07<00:06, 25.52it/s]
Loading 0:  52%|█████▏    | 190/363 [00:07<00:07, 23.41it/s]
Loading 0:  53%|█████▎    | 193/363 [00:08<00:06, 24.38it/s]
Loading 0:  54%|█████▍    | 196/363 [00:08<00:06, 24.54it/s]
Loading 0:  55%|█████▌    | 200/363 [00:22<00:06, 24.54it/s]
Loading 0:  55%|█████▌    | 201/363 [00:22<02:56,  1.09s/it]
Loading 0:  56%|█████▌    | 203/363 [00:22<02:25,  1.10it/s]
Loading 0:  57%|█████▋    | 208/363 [00:22<01:27,  1.77it/s]
Loading 0:  58%|█████▊    | 211/363 [00:22<01:07,  2.25it/s]
Loading 0:  59%|█████▉    | 214/363 [00:22<00:50,  2.95it/s]
Loading 0:  60%|██████    | 218/363 [00:23<00:34,  4.22it/s]
Loading 0:  61%|██████    | 221/363 [00:23<00:26,  5.37it/s]
Loading 0:  62%|██████▏   | 224/363 [00:23<00:21,  6.46it/s]
Loading 0:  63%|██████▎   | 229/363 [00:23<00:14,  9.49it/s]
Loading 0:  64%|██████▍   | 232/363 [00:23<00:11, 11.09it/s]
Loading 0:  65%|██████▌   | 237/363 [00:23<00:08, 15.11it/s]
Loading 0:  66%|██████▌   | 240/363 [00:23<00:07, 15.92it/s]
Loading 0:  68%|██████▊   | 246/363 [00:24<00:05, 21.47it/s]
Loading 0:  69%|██████▉   | 250/363 [00:24<00:05, 22.04it/s]
Loading 0:  70%|███████   | 255/363 [00:24<00:04, 25.64it/s]
Loading 0:  71%|███████▏  | 259/363 [00:24<00:04, 25.24it/s]
Loading 0:  73%|███████▎  | 266/363 [00:24<00:03, 30.89it/s]
Loading 0:  74%|███████▍  | 270/363 [00:25<00:04, 21.29it/s]
Loading 0:  75%|███████▌  | 274/363 [00:25<00:03, 23.98it/s]
Loading 0:  77%|███████▋  | 278/363 [00:25<00:03, 25.48it/s]
Loading 0:  78%|███████▊  | 282/363 [00:25<00:03, 22.62it/s]
Loading 0:  79%|███████▊  | 285/363 [00:25<00:03, 21.57it/s]
Loading 0:  80%|████████  | 291/363 [00:25<00:02, 26.74it/s]
Loading 0:  81%|████████  | 294/363 [00:25<00:02, 24.92it/s]
Loading 0:  82%|████████▏ | 299/363 [00:26<00:02, 27.92it/s]
Loading 0:  84%|████████▎ | 304/363 [00:26<00:02, 26.09it/s]
Loading 0:  85%|████████▍ | 307/363 [00:26<00:02, 23.62it/s]
Loading 0:  85%|████████▌ | 310/363 [00:26<00:02, 24.49it/s]
Loading 0:  86%|████████▌ | 313/363 [00:26<00:02, 24.75it/s]
Loading 0:  88%|████████▊ | 318/363 [00:26<00:01, 27.94it/s]
Loading 0:  88%|████████▊ | 321/363 [00:27<00:01, 25.28it/s]
Loading 0:  90%|█████████ | 327/363 [00:27<00:01, 30.55it/s]
Loading 0:  91%|█████████ | 331/363 [00:27<00:01, 28.76it/s]
Loading 0:  92%|█████████▏| 335/363 [00:27<00:00, 29.30it/s]
Loading 0:  93%|█████████▎| 338/363 [00:27<00:00, 28.16it/s]
Loading 0:  94%|█████████▍| 341/363 [00:27<00:01, 16.48it/s]
Loading 0:  96%|█████████▌| 347/363 [00:28<00:00, 22.02it/s]
Loading 0:  96%|█████████▋| 350/363 [00:28<00:00, 22.52it/s]
Loading 0:  98%|█████████▊| 355/363 [00:28<00:00, 26.12it/s]
Loading 0:  99%|█████████▊| 358/363 [00:28<00:00, 24.16it/s]
                                                            
Job chaiml-ssnew-v7-1a-dpo-cosine-v1-mkmlizer completed after 195.72s with status: succeeded
Stopping job with name chaiml-ssnew-v7-1a-dpo-cosine-v1-mkmlizer
Pipeline stage MKMLizer completed in 196.23s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.14s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-ssnew-v7-1a-dpo-cosine-v1
Waiting for inference service chaiml-ssnew-v7-1a-dpo-cosine-v1 to be ready
Inference service chaiml-ssnew-v7-1a-dpo-cosine-v1 ready after 151.0057511329651s
Pipeline stage MKMLDeployer completed in 151.73s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.2849457263946533s
Received healthy response to inference request in 1.8811888694763184s
Received healthy response to inference request in 1.9565954208374023s
Received healthy response to inference request in 1.70965576171875s
Received healthy response to inference request in 1.9070813655853271s
5 requests
0 failed requests
5th percentile: 1.7439623832702638
10th percentile: 1.7782690048217773
20th percentile: 1.8468822479248046
30th percentile: 1.8863673686981202
40th percentile: 1.8967243671417235
50th percentile: 1.9070813655853271
60th percentile: 1.9268869876861572
70th percentile: 1.9466926097869872
80th percentile: 2.022265481948853
90th percentile: 2.153605604171753
95th percentile: 2.219275665283203
99th percentile: 2.271811714172363
mean time: 1.9478934288024903
Pipeline stage StressChecker completed in 11.14s
run pipeline stage %s
Running pipeline stage OfflineFamilyFriendlyTriggerPipeline
run_pipeline:run_in_cloud %s
starting trigger_guanaco_pipeline args=%s
triggered trigger_guanaco_pipeline args=%s
Pipeline stage OfflineFamilyFriendlyTriggerPipeline completed in 0.79s
run pipeline stage %s
Running pipeline stage TriggerMKMLProfilingPipeline
run_pipeline:run_in_cloud %s
starting trigger_guanaco_pipeline args=%s
triggered trigger_guanaco_pipeline args=%s
Pipeline stage TriggerMKMLProfilingPipeline completed in 0.63s
Shutdown handler de-registered
chaiml-ssnew-v7-1a-dpo-cosine_v1 status is now deployed due to DeploymentManager action
Shutdown handler registered
run pipeline %s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Skipping teardown as no inference service was successfully deployed
Pipeline stage MKMLProfilerDeleter completed in 0.10s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.09s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service chaiml-ssnew-v7-1a-dpo-cosine-v1-profiler
Waiting for inference service chaiml-ssnew-v7-1a-dpo-cosine-v1-profiler to be ready
Shutdown handler registered
run pipeline %s
run pipeline stage %s
Running pipeline stage OfflineFamilyFriendlyScorer
Evaluating %s Family Friendly Score with %s threads
Pipeline stage OfflineFamilyFriendlyScorer completed in 2772.22s
Shutdown handler de-registered
chaiml-ssnew-v7-1a-dpo-cosine_v1 status is now inactive due to auto deactivation removed underperforming models
chaiml-ssnew-v7-1a-dpo-cosine_v1 status is now torndown due to DeploymentManager action